Skip to content

Commit 93b054b

Browse files
mintlify[bot]mintlify[bot]
authored
Add Kandinsky 5.0 video generation tutorial (#630)
* Update tutorials/video/kandinsky/kandinsky-5.mdx Co-Authored-By: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com> * Update docs.json Co-Authored-By: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com> * Update tutorials/video/kandinsky/kandinsky-5.mdx Co-Authored-By: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com> * Update tutorials/video/kandinsky/kandinsky-5.mdx Co-Authored-By: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com> * Update tutorials/video/kandinsky/kandinsky-5.mdx Co-Authored-By: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com> * Update zh-CN/tutorials/video/kandinsky/kandinsky-5.mdx Co-Authored-By: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com> * Update docs.json Co-Authored-By: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com> --------- Co-authored-by: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com>
1 parent c661ff6 commit 93b054b

File tree

3 files changed

+234
-0
lines changed

3 files changed

+234
-0
lines changed

‎docs.json‎

Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -204,6 +204,12 @@
204204
"pages": [
205205
"tutorials/video/cosmos/cosmos-predict2-video2world"
206206
]
207+
},
208+
{
209+
"group": "Kandinsky",
210+
"pages": [
211+
"tutorials/video/kandinsky/kandinsky-5"
212+
]
207213
}
208214
]
209215
},
@@ -834,6 +840,12 @@
834840
"pages": [
835841
"zh-CN/tutorials/video/cosmos/cosmos-predict2-video2world"
836842
]
843+
},
844+
{
845+
"group": "Kandinsky",
846+
"pages": [
847+
"zh-CN/tutorials/video/kandinsky/kandinsky-5"
848+
]
837849
}
838850
]
839851
},

‎tutorials/video/kandinsky/kandinsky-5.mdx‎

Lines changed: 111 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,111 @@
1+
---
2+
title: "Kandinsky 5.0"
3+
description: "This guide shows how to use Kandinsky 5.0 video generation workflows in ComfyUI"
4+
sidebarTitle: "Kandinsky 5.0"
5+
---
6+
7+
import UpdateReminder from "/snippets/tutorials/update-reminder.mdx";
8+
9+
[Kandinsky 5.0](https://huggingface.co/kandinskylab/Kandinsky-5.0-I2V-Lite-5s) is a family of diffusion models for video and image generation developed by [Kandinsky Lab](https://huggingface.co/kandinskylab). The Kandinsky 5.0 T2V Lite is a lightweight 2B parameter model that ranks among the top open-source video generation models, capable of generating videos up to 10 seconds long.
10+
11+
<UpdateReminder/>
12+
13+
## Overview
14+
15+
Kandinsky 5.0 uses a latent diffusion pipeline with Flow Matching and features:
16+
17+
- **Diffusion Transformer (DiT):** Main generative backbone with cross-attention to text embeddings
18+
- **Qwen2.5-VL and CLIP:** Provides high-quality text embeddings
19+
- **HunyuanVideo 3D VAE:** Encodes and decodes video into a latent space
20+
21+
The model family includes multiple variants optimized for different use cases:
22+
- **SFT model:** Highest generation quality
23+
- **CFG-distilled:** 2× faster inference
24+
- **Diffusion-distilled:** 6× faster with minimal quality loss (16 steps)
25+
- **Pretrain model:** Designed for fine-tuning
26+
27+
All models are available in 5-second and 10-second video generation versions.
28+
29+
## Model variants
30+
31+
| Model | Video Duration | NFE | Latency (H100) |
32+
|-------|---------------|-----|----------------|
33+
| Kandinsky 5.0 T2V Lite SFT | 5s / 10s | 100 | 139s / 224s |
34+
| Kandinsky 5.0 T2V Lite no-CFG | 5s / 10s | 50 | 77s / 124s |
35+
| Kandinsky 5.0 T2V Lite distill | 5s / 10s | 16 | 35s / 61s |
36+
| Kandinsky 5.0 I2V Lite | 5s | 100 | 673s |
37+
38+
## Text-to-Video workflow
39+
40+
### 1. Download workflow file
41+
42+
Please update your ComfyUI to the latest version, and through the menu `Workflow` -> `Browse Templates` -> `Video`, find "Kandinsky 5.0 T2V" to load the workflow.
43+
44+
<a className="prose" target='_blank' href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/video_kandinsky5_t2v.json" style={{ display: 'inline-block', backgroundColor: '#0078D6', color: '#ffffff', padding: '10px 20px', borderRadius: '8px', borderColor: "transparent", textDecoration: 'none', fontWeight: 'bold'}}>
45+
<p className="prose" style={{ margin: 0, fontSize: "0.8rem" }}>Download JSON Workflow File</p>
46+
</a>
47+
48+
### 2. Manually download models
49+
50+
**Text Encoders**
51+
- [qwen_2.5_vl_7b_fp8_scaled.safetensors](https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors)
52+
- [clip_l.safetensors](https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors)
53+
54+
**Diffusion Model**
55+
- [kandinsky5lite_t2v_sft_5s.safetensors](https://huggingface.co/kandinskylab/Kandinsky-5.0-T2V-Lite-sft-5s/resolve/main/model/kandinsky5lite_t2v_sft_5s.safetensors)
56+
57+
**VAE**
58+
- [hunyuan_video_vae_bf16.safetensors](https://huggingface.co/Kijai/HunyuanVideo_comfy/resolve/main/hunyuan_video_vae_bf16.safetensors)
59+
60+
```
61+
ComfyUI/
62+
├── 📂 models/
63+
│ ├── 📂 text_encoders/
64+
│ │ ├── qwen_2.5_vl_7b_fp8_scaled.safetensors
65+
│ │ └── clip_l.safetensors
66+
│ ├── 📂 diffusion_models/
67+
│ │ └── kandinsky5lite_t2v_sft_5s.safetensors
68+
│ └── 📂 vae/
69+
│ └── hunyuan_video_vae_bf16.safetensors
70+
```
71+
72+
## Image-to-Video workflow
73+
74+
### 1. Download workflow file
75+
76+
Please update your ComfyUI to the latest version, and through the menu `Workflow` -> `Browse Templates` -> `Video`, find "Kandinsky 5.0 I2V" to load the workflow.
77+
78+
<a className="prose" target='_blank' href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/video_kandinsky5_i2v.json" style={{ display: 'inline-block', backgroundColor: '#0078D6', color: '#ffffff', padding: '10px 20px', borderRadius: '8px', borderColor: "transparent", textDecoration: 'none', fontWeight: 'bold'}}>
79+
<p className="prose" style={{ margin: 0, fontSize: "0.8rem" }}>Download JSON Workflow File</p>
80+
</a>
81+
82+
### 2. Manually download models
83+
84+
**Text Encoders**
85+
- [qwen_2.5_vl_7b_fp8_scaled.safetensors](https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors)
86+
- [clip_l.safetensors](https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors)
87+
88+
**Diffusion Model**
89+
- [kandinsky5lite_i2v_sft_5s.safetensors](https://huggingface.co/kandinskylab/Kandinsky-5.0-I2V-Lite-5s/resolve/main/model/kandinsky5lite_i2v_sft_5s.safetensors)
90+
91+
**VAE**
92+
- [hunyuan_video_vae_bf16.safetensors](https://huggingface.co/Kijai/HunyuanVideo_comfy/resolve/main/hunyuan_video_vae_bf16.safetensors)
93+
94+
```
95+
ComfyUI/
96+
├── 📂 models/
97+
│ ├── 📂 text_encoders/
98+
│ │ ├── qwen_2.5_vl_7b_fp8_scaled.safetensors
99+
│ │ └── clip_l.safetensors
100+
│ ├── 📂 diffusion_models/
101+
│ │ └── kandinsky5lite_i2v_sft_5s.safetensors
102+
│ └── 📂 vae/
103+
│ └── hunyuan_video_vae_bf16.safetensors
104+
```
105+
106+
## Resources
107+
108+
- [HuggingFace Model Collection](https://huggingface.co/collections/kandinskylab/kandinsky-50-video-lite)
109+
- [GitHub Repository](https://github.com/ai-forever/Kandinsky-5)
110+
- [ComfyUI Integration](https://github.com/ai-forever/Kandinsky-5/blob/main/comfyui/README.md)
111+
- [Project Page](https://ai-forever.github.io/Kandinsky-5/)

‎zh-CN/tutorials/video/kandinsky/kandinsky-5.mdx‎

Lines changed: 111 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,111 @@
1+
---
2+
title: "Kandinsky 5.0"
3+
description: "本指南介绍如何在 ComfyUI 中使用 Kandinsky 5.0 视频生成工作流"
4+
sidebarTitle: "Kandinsky 5.0"
5+
---
6+
7+
import UpdateReminder from "/snippets/zh/tutorials/update-reminder.mdx";
8+
9+
[Kandinsky 5.0](https://huggingface.co/kandinskylab/Kandinsky-5.0-I2V-Lite-5s) 是由 [Kandinsky Lab](https://huggingface.co/kandinskylab) 开发的视频和图像生成扩散模型系列。Kandinsky 5.0 T2V Lite 是一个轻量级的 2B 参数模型，在开源视频生成模型中名列前茅，能够生成长达 10 秒的视频。
10+
11+
<UpdateReminder/>
12+
13+
## 概述
14+
15+
Kandinsky 5.0 使用带有 Flow Matching 的潜在扩散管道，具有以下特点：
16+
17+
- **扩散 Transformer (DiT)：** 主要生成骨干网络，通过交叉注意力连接文本嵌入
18+
- **Qwen2.5-VL 和 CLIP：** 提供高质量的文本嵌入
19+
- **HunyuanVideo 3D VAE：** 将视频编码和解码到潜在空间
20+
21+
该模型系列包含多个针对不同用例优化的变体：
22+
- **SFT 模型：** 最高生成质量
23+
- **CFG-distilled：** 推理速度提升 2 倍
24+
- **Diffusion-distilled：** 速度提升 6 倍，质量损失极小（16 步）
25+
- **Pretrain 模型：** 专为微调设计
26+
27+
所有模型均提供 5 秒和 10 秒视频生成版本。
28+
29+
## 模型变体
30+
31+
| 模型 | 视频时长 | NFE | 延迟 (H100) |
32+
|-------|---------------|-----|----------------|
33+
| Kandinsky 5.0 T2V Lite SFT | 5s / 10s | 100 | 139s / 224s |
34+
| Kandinsky 5.0 T2V Lite no-CFG | 5s / 10s | 50 | 77s / 124s |
35+
| Kandinsky 5.0 T2V Lite distill | 5s / 10s | 16 | 35s / 61s |
36+
| Kandinsky 5.0 I2V Lite | 5s | 100 | 673s |
37+
38+
## 文生视频工作流
39+
40+
### 1. 下载工作流文件
41+
42+
请更新你的 ComfyUI 到最新版本，并通过菜单 `工作流` -> `浏览模板` -> `视频` 找到 "Kandinsky 5.0 T2V" 以加载工作流。
43+
44+
<a className="prose" target='_blank' href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/video_kandinsky5_t2v.json" style={{ display: 'inline-block', backgroundColor: '#0078D6', color: '#ffffff', padding: '10px 20px', borderRadius: '8px', borderColor: "transparent", textDecoration: 'none', fontWeight: 'bold'}}>
45+
<p className="prose" style={{ margin: 0, fontSize: "0.8rem" }}>下载 JSON 格式工作流</p>
46+
</a>
47+
48+
### 2. 手动下载模型
49+
50+
**Text Encoders**
51+
- [qwen_2.5_vl_7b_fp8_scaled.safetensors](https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors)
52+
- [clip_l.safetensors](https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors)
53+
54+
**Diffusion Model**
55+
- [kandinsky5lite_t2v_sft_5s.safetensors](https://huggingface.co/kandinskylab/Kandinsky-5.0-T2V-Lite-sft-5s/resolve/main/model/kandinsky5lite_t2v_sft_5s.safetensors)
56+
57+
**VAE**
58+
- [hunyuan_video_vae_bf16.safetensors](https://huggingface.co/Kijai/HunyuanVideo_comfy/resolve/main/hunyuan_video_vae_bf16.safetensors)
59+
60+
```
61+
ComfyUI/
62+
├── 📂 models/
63+
│ ├── 📂 text_encoders/
64+
│ │ ├── qwen_2.5_vl_7b_fp8_scaled.safetensors
65+
│ │ └── clip_l.safetensors
66+
│ ├── 📂 diffusion_models/
67+
│ │ └── kandinsky5lite_t2v_sft_5s.safetensors
68+
│ └── 📂 vae/
69+
│ └── hunyuan_video_vae_bf16.safetensors
70+
```
71+
72+
## 图生视频工作流
73+
74+
### 1. 下载工作流文件
75+
76+
请更新你的 ComfyUI 到最新版本，并通过菜单 `工作流` -> `浏览模板` -> `视频` 找到 "Kandinsky 5.0 I2V" 以加载工作流。
77+
78+
<a className="prose" target='_blank' href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/video_kandinsky5_i2v.json" style={{ display: 'inline-block', backgroundColor: '#0078D6', color: '#ffffff', padding: '10px 20px', borderRadius: '8px', borderColor: "transparent", textDecoration: 'none', fontWeight: 'bold'}}>
79+
<p className="prose" style={{ margin: 0, fontSize: "0.8rem" }}>下载 JSON 格式工作流</p>
80+
</a>
81+
82+
### 2. 手动下载模型
83+
84+
**Text Encoders**
85+
- [qwen_2.5_vl_7b_fp8_scaled.safetensors](https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors)
86+
- [clip_l.safetensors](https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors)
87+
88+
**Diffusion Model**
89+
- [kandinsky5lite_i2v_sft_5s.safetensors](https://huggingface.co/kandinskylab/Kandinsky-5.0-I2V-Lite-5s/resolve/main/model/kandinsky5lite_i2v_sft_5s.safetensors)
90+
91+
**VAE**
92+
- [hunyuan_video_vae_bf16.safetensors](https://huggingface.co/Kijai/HunyuanVideo_comfy/resolve/main/hunyuan_video_vae_bf16.safetensors)
93+
94+
```
95+
ComfyUI/
96+
├── 📂 models/
97+
│ ├── 📂 text_encoders/
98+
│ │ ├── qwen_2.5_vl_7b_fp8_scaled.safetensors
99+
│ │ └── clip_l.safetensors
100+
│ ├── 📂 diffusion_models/
101+
│ │ └── kandinsky5lite_i2v_sft_5s.safetensors
102+
│ └── 📂 vae/
103+
│ └── hunyuan_video_vae_bf16.safetensors
104+
```
105+
106+
## 资源
107+
108+
- [HuggingFace 模型合集](https://huggingface.co/collections/kandinskylab/kandinsky-50-video-lite)
109+
- [GitHub 仓库](https://github.com/ai-forever/Kandinsky-5)
110+
- [ComfyUI 集成](https://github.com/ai-forever/Kandinsky-5/blob/main/comfyui/README.md)
111+
- [项目主页](https://ai-forever.github.io/Kandinsky-5/)

0 commit comments

Comments
 (0)